metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wikipedia
model-index:
- name: oknashar-bert
results: []
oknashar-bert
This model is a fine-tuned version of mosaicml/mosaic-bert-base on the wikipedia dataset. It achieves the following results on the evaluation set:
- eval_loss: 7.6172
- eval_runtime: 68.6888
- eval_samples_per_second: 22.813
- eval_steps_per_second: 0.364
- epoch: 2.84
- step: 500
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 10
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 80
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Framework versions
- Transformers 4.18.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.12.1